Agent Lab — a live forecast exhibit · Applied AI
← All fixtures
Group A · Matchday 8 · 2026-06-18

Czech Republic vs South Africa

Atlanta, United States · neutral venue

Most likely scoreline
1–0 15.0%
45.5%
CZE win
28.9%
Draw
25.5%
RSA win
Top scorelines
  • 1–0 15.0%
  • 0–0 14.8%
  • 1–1 10.8%
  • 0–1 10.6%
Total goals
0 to 10 goals · most likely → tallest

The agent’s call

3-agent ensemble · deepseek-chat
CZE win
52.3%
Draw
28.0%
RSA win
19.7%

The model prior gives Czech Republic a 46% home win probability, but the supplied intel justifies a moderate upward adjustment. Czech Republic's recent form (WDDWW) is clearly superior to South Africa's (LDLDD). More importantly, the key player analysis reveals a significant squad quality gap: Czech key players are at top European clubs (Bayer Leverkusen, West Ham, Lyon) while South Africa's are mostly at Mamelodi Sundowns or lower-tier European sides. This gap in individual quality, combined with the form disparity, outweighs the lack of head-to-head or conditions factors. I increase home win to 52%, slightly reduce draw to 28%, and away win to 20%. The model expected goals (CZE 1.27, RSA 0.83) suggest a low-scoring match, and the top model scorelines (1-0, 0-0, 1-1) are plausible. The quality gap adds a bit more confidence for Czech Republic to score, but South Africa's defensive solidity (recent draws) keeps the 0-0 and 1-1 possibilities. I keep the scoreline distribution similar to the model, slightly shifting probability toward 1-0 and 2-0 at the expense of 0-1 and 0-2.

What the agent weighed
What the agent checked on the web
Searched tavily for CZE · RSA — 6 sources kept
Agent scorelines
generated 2026-06-11
Last 5 — CZE
-0.13 pts/match vs model expectation · opp. avg #51
  • REP #50 -0.7
  • DEN #14 -0.1
  • KOS #56 +1.1
  • GUA #100 +0.5
  • KOR #37 -1.3
GF / GA last 10: 19 / 11
Last 5 — RSA
-0.92 pts/match vs model expectation · opp. avg #83
  • PAN #74 -0.7
  • PAN #74 -1.7
  • NIC #151 -1.5
  • JAM #94 -0.5
  • MEX #21 -0.7
GF / GA last 10: 12 / 13
Head-to-head (last 5)
  • 1997-12-13 South Africa 2–2 Czech Republic
▸ Full score grid (7×7)
P(home goals × away goals), %
0
1
2
3
4
5
6
0
14.8
10.6
4.6
1.5
0.4
0.1
0.0
1
15.0
10.8
4.6
1.5
0.4
0.1
0.0
2
9.2
6.6
2.8
0.9
0.3
0.1
0.0
3
4.4
3.1
1.3
0.4
0.1
0.0
0.0
4
1.8
1.3
0.5
0.2
0.1
0.0
0.0
5
0.7
0.5
0.2
0.1
0.0
0.0
0.0
6
0.2
0.2
0.1
0.0
0.0
0.0
0.0

Rows = CZE goals; columns = RSA goals. Above-diagonal cells are home wins; diagonal = draws; below = away wins. Truncated at 6 — the joint mass past that is < 1 %.

Expected goals (Poisson rate, λ)
1.28
CZE
0.84
RSA

Independent-Poisson rates. W/D/L and the score grid integrate the full 13×13 joint under these two parameters.

News context — injuries, suspensions, projected XI — is not part of the model, which sees only past results.